octeontx2-pf: cn10k: Use runtime allocated LMTLINE region

The current driver uses static LMTST region allocated by firmware.
This memory gets populated as PF/VF BAR2. RVU PF/VF driver ioremap
the memory as device memory for NIX/NPA operation. Since the memory
is mapped as device memory we see performance degration. To address
this issue this patch implements runtime memory allocation.
RVU PF/VF allocates memory during device probe and share the base
address with RVU AF. RVU AF then configure the LMT MAP table
accordingly.

Signed-off-by: Geetha sowjanya <gakula@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Author: Geetha sowjanya

drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c

@@ -22,69 +22,52 @@ static struct dev_hw_ops cn10k_hw_ops = {
 	.refill_pool_ptrs = cn10k_refill_pool_ptrs,
 };
 
-int cn10k_pf_lmtst_init(struct otx2_nic *pf)
+int cn10k_lmtst_init(struct otx2_nic *pfvf)
 {
-	int size, num_lines;
-	u64 base;
 
-	if (!test_bit(CN10K_LMTST, &pf->hw.cap_flag)) {
-		pf->hw_ops = &otx2_hw_ops;
+	struct lmtst_tbl_setup_req *req;
+	int qcount, err;
+
+	if (!test_bit(CN10K_LMTST, &pfvf->hw.cap_flag)) {
+		pfvf->hw_ops = &otx2_hw_ops;
 		return 0;
 	}
 
-	pf->hw_ops = &cn10k_hw_ops;
-	base = pci_resource_start(pf->pdev, PCI_MBOX_BAR_NUM) +
-		       (MBOX_SIZE * (pf->total_vfs + 1));
-
-	size = pci_resource_len(pf->pdev, PCI_MBOX_BAR_NUM) -
-	       (MBOX_SIZE * (pf->total_vfs + 1));
-
-	pf->hw.lmt_base = ioremap(base, size);
+	pfvf->hw_ops = &cn10k_hw_ops;
+	qcount = pfvf->hw.max_queues;
+	/* LMTST lines allocation
+	 * qcount = num_online_cpus();
+	 * NPA = TX + RX + XDP.
+	 * NIX = TX * 32 (For Burst SQE flush).
+	 */
+	pfvf->tot_lmt_lines = (qcount * 3) + (qcount * 32);
+	pfvf->npa_lmt_lines = qcount * 3;
+	pfvf->nix_lmt_size =  LMT_BURST_SIZE * LMT_LINE_SIZE;
 
-	if (!pf->hw.lmt_base) {
-		dev_err(pf->dev, "Unable to map PF LMTST region\n");
+	mutex_lock(&pfvf->mbox.lock);
+	req = otx2_mbox_alloc_msg_lmtst_tbl_setup(&pfvf->mbox);
+	if (!req) {
+		mutex_unlock(&pfvf->mbox.lock);
 		return -ENOMEM;
 	}
 
-	/* FIXME: Get the num of LMTST lines from LMT table */
-	pf->tot_lmt_lines = size / LMT_LINE_SIZE;
-	num_lines = (pf->tot_lmt_lines - NIX_LMTID_BASE) /
-			    pf->hw.tx_queues;
-	/* Number of LMT lines per SQ queues */
-	pf->nix_lmt_lines = num_lines > 32 ? 32 : num_lines;
-
-	pf->nix_lmt_size = pf->nix_lmt_lines * LMT_LINE_SIZE;
-	return 0;
-}
+	req->use_local_lmt_region = true;
 
-int cn10k_vf_lmtst_init(struct otx2_nic *vf)
-{
-	int size, num_lines;
-
-	if (!test_bit(CN10K_LMTST, &vf->hw.cap_flag)) {
-		vf->hw_ops = &otx2_hw_ops;
-		return 0;
+	err = qmem_alloc(pfvf->dev, &pfvf->dync_lmt, pfvf->tot_lmt_lines,
+			 LMT_LINE_SIZE);
+	if (err) {
+		mutex_unlock(&pfvf->mbox.lock);
+		return err;
 	}
+	pfvf->hw.lmt_base = (u64 *)pfvf->dync_lmt->base;
+	req->lmt_iova = (u64)pfvf->dync_lmt->iova;
 
-	vf->hw_ops = &cn10k_hw_ops;
-	size = pci_resource_len(vf->pdev, PCI_MBOX_BAR_NUM);
-	vf->hw.lmt_base = ioremap_wc(pci_resource_start(vf->pdev,
-							PCI_MBOX_BAR_NUM),
-				     size);
-	if (!vf->hw.lmt_base) {
-		dev_err(vf->dev, "Unable to map VF LMTST region\n");
-		return -ENOMEM;
-	}
+	err = otx2_sync_mbox_msg(&pfvf->mbox);
+	mutex_unlock(&pfvf->mbox.lock);
 
-	vf->tot_lmt_lines = size / LMT_LINE_SIZE;
-	/* LMTST lines per SQ */
-	num_lines = (vf->tot_lmt_lines - NIX_LMTID_BASE) /
-			    vf->hw.tx_queues;
-	vf->nix_lmt_lines = num_lines > 32 ? 32 : num_lines;
-	vf->nix_lmt_size = vf->nix_lmt_lines * LMT_LINE_SIZE;
 	return 0;
 }
-EXPORT_SYMBOL(cn10k_vf_lmtst_init);
+EXPORT_SYMBOL(cn10k_lmtst_init);
 
 int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura)
 {
@@ -93,9 +76,11 @@ int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura)
 	struct otx2_snd_queue *sq;
 
 	sq = &pfvf->qset.sq[qidx];
-	sq->lmt_addr = (__force u64 *)((u64)pfvf->hw.nix_lmt_base +
+	sq->lmt_addr = (u64 *)((u64)pfvf->hw.nix_lmt_base +
 			       (qidx * pfvf->nix_lmt_size));
 
+	sq->lmt_id = pfvf->npa_lmt_lines + (qidx * LMT_BURST_SIZE);
+
 	/* Get memory to put this msg */
 	aq = otx2_mbox_alloc_msg_nix_cn10k_aq_enq(&pfvf->mbox);
 	if (!aq)
@@ -158,15 +143,13 @@ void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
 
 void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx)
 {
-	struct otx2_nic *pfvf = dev;
-	int lmt_id = NIX_LMTID_BASE + (qidx * pfvf->nix_lmt_lines);
 	u64 val = 0, tar_addr = 0;
 
 	/* FIXME: val[0:10] LMT_ID.
 	 * [12:15] no of LMTST - 1 in the burst.
 	 * [19:63] data size of each LMTST in the burst except first.
 	 */
-	val = (lmt_id & 0x7FF);
+	val = (sq->lmt_id & 0x7FF);
 	/* Target address for LMTST flush tells HW how many 128bit
 	 * words are present.
 	 * tar_addr[6:4] size of first LMTST - 1 in units of 128b.

drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h

@@ -12,8 +12,7 @@
 void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq);
 void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx);
 int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura);
-int cn10k_pf_lmtst_init(struct otx2_nic *pf);
-int cn10k_vf_lmtst_init(struct otx2_nic *vf);
+int cn10k_lmtst_init(struct otx2_nic *pfvf);
 int cn10k_free_all_ipolicers(struct otx2_nic *pfvf);
 int cn10k_alloc_matchall_ipolicer(struct otx2_nic *pfvf);
 int cn10k_free_matchall_ipolicer(struct otx2_nic *pfvf);

drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h

@@ -218,8 +218,8 @@ struct otx2_hw {
 	unsigned long		cap_flag;
 
 #define LMT_LINE_SIZE		128
-#define NIX_LMTID_BASE		72 /* RX + TX + XDP */
-	void __iomem		*lmt_base;
+#define LMT_BURST_SIZE		32 /* 32 LMTST lines for burst SQE flush */
+	u64			*lmt_base;
 	u64			*npa_lmt_base;
 	u64			*nix_lmt_base;
 };
@@ -363,8 +363,9 @@ struct otx2_nic {
 	/* Block address of NIX either BLKADDR_NIX0 or BLKADDR_NIX1 */
 	int			nix_blkaddr;
 	/* LMTST Lines info */
+	struct qmem		*dync_lmt;
 	u16			tot_lmt_lines;
-	u16			nix_lmt_lines;
+	u16			npa_lmt_lines;
 	u32			nix_lmt_size;
 
 	struct otx2_ptp		*ptp;

drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c

@@ -1533,10 +1533,10 @@ int otx2_open(struct net_device *netdev)
 
 	if (test_bit(CN10K_LMTST, &pf->hw.cap_flag)) {
 		/* Reserve LMT lines for NPA AURA batch free */
-		pf->hw.npa_lmt_base = (__force u64 *)pf->hw.lmt_base;
+		pf->hw.npa_lmt_base = pf->hw.lmt_base;
 		/* Reserve LMT lines for NIX TX */
-		pf->hw.nix_lmt_base = (__force u64 *)((u64)pf->hw.npa_lmt_base +
-				      (NIX_LMTID_BASE * LMT_LINE_SIZE));
+		pf->hw.nix_lmt_base = (u64 *)((u64)pf->hw.npa_lmt_base +
+				      (pf->npa_lmt_lines * LMT_LINE_SIZE));
 	}
 
 	err = otx2_init_hw_resources(pf);
@@ -2526,7 +2526,7 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (err)
 		goto err_detach_rsrc;
 
-	err = cn10k_pf_lmtst_init(pf);
+	err = cn10k_lmtst_init(pf);
 	if (err)
 		goto err_detach_rsrc;
 
@@ -2630,8 +2630,8 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 err_ptp_destroy:
 	otx2_ptp_destroy(pf);
 err_detach_rsrc:
-	if (hw->lmt_base)
-		iounmap(hw->lmt_base);
+	if (test_bit(CN10K_LMTST, &pf->hw.cap_flag))
+		qmem_free(pf->dev, pf->dync_lmt);
 	otx2_detach_resources(&pf->mbox);
 err_disable_mbox_intr:
 	otx2_disable_mbox_intr(pf);
@@ -2772,9 +2772,8 @@ static void otx2_remove(struct pci_dev *pdev)
 	otx2_mcam_flow_del(pf);
 	otx2_shutdown_tc(pf);
 	otx2_detach_resources(&pf->mbox);
-	if (pf->hw.lmt_base)
-		iounmap(pf->hw.lmt_base);
-
+	if (test_bit(CN10K_LMTST, &pf->hw.cap_flag))
+		qmem_free(pf->dev, pf->dync_lmt);
 	otx2_disable_mbox_intr(pf);
 	otx2_pfaf_mbox_destroy(pf);
 	pci_free_irq_vectors(pf->pdev);

drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h

@@ -83,6 +83,7 @@ struct otx2_snd_queue {
 	u16			num_sqbs;
 	u16			sqe_thresh;
 	u8			sqe_per_sqb;
+	u32			lmt_id;
 	u64			 io_addr;
 	u64			*aura_fc_addr;
 	u64			*lmt_addr;

drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c

@@ -609,7 +609,7 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (err)
 		goto err_detach_rsrc;
 
-	err = cn10k_vf_lmtst_init(vf);
+	err = cn10k_lmtst_init(vf);
 	if (err)
 		goto err_detach_rsrc;
 
@@ -667,8 +667,8 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 err_unreg_netdev:
 	unregister_netdev(netdev);
 err_detach_rsrc:
-	if (hw->lmt_base)
-		iounmap(hw->lmt_base);
+	if (test_bit(CN10K_LMTST, &vf->hw.cap_flag))
+		qmem_free(vf->dev, vf->dync_lmt);
 	otx2_detach_resources(&vf->mbox);
 err_disable_mbox_intr:
 	otx2vf_disable_mbox_intr(vf);
@@ -700,10 +700,8 @@ static void otx2vf_remove(struct pci_dev *pdev)
 		destroy_workqueue(vf->otx2_wq);
 	otx2vf_disable_mbox_intr(vf);
 	otx2_detach_resources(&vf->mbox);
-
-	if (vf->hw.lmt_base)
-		iounmap(vf->hw.lmt_base);
-
+	if (test_bit(CN10K_LMTST, &vf->hw.cap_flag))
+		qmem_free(vf->dev, vf->dync_lmt);
 	otx2vf_vfaf_mbox_destroy(vf);
 	pci_free_irq_vectors(vf->pdev);
 	pci_set_drvdata(pdev, NULL);